Viewing profile — danoandco

Definitely and Twill is for SWE delegation first, not so much the “general agent on my machine.”

It's a crowded market. On the CLI-agnostic cloud agent positioning, there are only startups so far. Only incumbent is Github Agents as you mentioned in another thread.

Yes, broadly. The main structural difference is that we’re agent-agnostic, so we can combine lab-native CLIs in one workflow. GitHub will likely struggle there because they have di…

On gh-aw: it looks solid for the event-driven automation shape (triage, docs sync, CI fix). We're after a slightly different shape: interactive back-and-forth, steering from Slack …

Mmh this works on my end. Sending you an email. Ty

On computer use: Yes. Sandboxes come with a computer-use CLI for driving Linux GUI apps via X11. On triggers: Cron, GitHub (PRs, issues, @twill mentions in review comments), Slack,…

Awesome! Thanks for trying it.

Jules is similar to Twill with the following differences: - Twill is CLI-agnostic, meaning you can use Claude Code, Codex or Gemini. Jules only works with Gemini. - We focus on the…

On the Twill web app, you can run the same task across different agents and multiple attempts (each in its own sandbox). Then you pick the best result. This is super handy for UI w…

Similar but reusing lab-native CLIs like Claude Code or Codex, which they perform RL on. And so in the long-run, we believe this approach wins over custom harnesses.

We’re focused on SWE use cases. Code is nice because there’s already a built-in verification loop: diffs, tests, CI, review, rollback. But you do quickly get to a state where the a…

Totally right on the compile time. CIs have the same bottleneck, and the ecosystem is working on fixing this (faster cpus, better caching) in both coding agents and CI to improve o…

[dead]

For a solo dev running one task at a time, a beefy desktop overnight is totally viable. We see a lot of this with the Mac Mini hype Cloud starts to matter when you want to (a) run …

Yes, this is the pass@k metric from code generation research. Found the relevant paper Evaluating Large Language Models Trained on Code (Chen et al., 2021) which introduced the met…

Claude managed agents is a general-purpose hosted runtime for Claude. While Twill focuses on SWE tasks. And so the SWE workflow is pre-built (research, planning, verification, PR, …

Hey HN, we're Willy and Dan, co-founders of Twill.ai ( https://twill.ai/ ). Twill runs coding CLIs like Claude Code and Codex in isolated cloud sandboxes. You hand it work through …

Thanks for running it and the feedback! For the ADR vs AGENTS: CLIs usually load the AGENTS.md with a tag saying: "this context may or may not be relevant to your tasks. You should…

true, i think the key thing is explaining somewhere in the repo "why" something was done. like the rationale for choosing X over Y service for instance. maybe this record is just t…

OpenAI published an article and demo for scoring how well AI agents can work in a codebase ( https://openai.com/index/harness-engineering/ , https://www.youtube.com/watch?v=rhsSqr0…

reminds me of the "memory for agents is a moat" but for software memory for software